STN-OCR: A single Neural Network for Text Detection and Text Recognition
arXiv:1707.08831
Abstract
Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In re- cent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present STN-OCR, a step towards semi-supervised neural networks for scene text recognition, that can be optimized end-to-end. In contrast to most existing works that consist of multiple deep neural networks and several pre-processing steps we propose to use a single deep neural network that learns to detect and recognize text from natural images in a semi-supervised way. STN-OCR is a network that integrates and jointly learns a spatial transformer network, that can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We investigate how our model behaves on a range of different tasks (detection and recognition of characters, and lines of text). Experimental results on public benchmark datasets show the ability of our model to handle a variety of different tasks, without substantial changes in its overall network structure.
9 pages, 6 figures
References in corpus (5)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Synthetic Data for Text Localisation in Natural Images
- Recurrent Spatial Transformer Networks
- TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild
Cited by in corpus (6)
- Double Supervised Network with Attention Mechanism for Scene Text Recognition
- Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
- Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
- An end-to-end, interactive Deep Learning based Annotation system for cursive and print English handwritten text
- Financial ticket intelligent recognition system based on deep learning
- A Novel Integrated Framework for Learning both Text Detection and Recognition